I’m doing that with docker compose in my homelab, it’s pretty neat!

services:
  ollama:
    volumes:
      - /etc/ollama-docker/ollama:/root/.ollama
    container_name: ollama
    pull_policy: always
    tty: true
    restart: unless-stopped
    image: ollama/ollama
    ports:
      - 11434:11434
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0']
              capabilities:
                - gpu

  open-webui:
    build:
      context: .
      args:
        OLLAMA_BASE_URL: '/ollama'
      dockerfile: Dockerfile
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    volumes:
      - /etc/ollama-docker/open-webui:/app/backend/data
    depends_on:
      - ollama
    ports:
      - 3000:8080
    environment:
      - 'OLLAMA_BASE_URL=http://ollama:11434/'
      - 'WEBUI_SECRET_KEY='
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped

volumes:
  ollama: {}
  open-webui: {}

Sure! I mostly followed this random youtuber’s video for getting Wyoming protocols offloaded (Whisper/Piper), but he didn’t get Ollama to use his GPU: https://youtu.be/XvbVePuP7NY.

For getting the Nvidia/Docker passthrough, I used this guide: https://www.bittenbypython.com/en/posts/install_ollama_openwebui_ubuntu_nvidia/.

It’s working fairly great at this point!

It is, and it’s been revived! https://github.com/maforget/ComicRackCE

I spun up a new Plex server with a decent GPU - and decided to try offloading Home Assistant’s Preview Voice Assistant TTS/STT to it. That’s all working as of yesterday, including an Ollama LLM for processing.

Last on my list is figuring out how to get Home Assistant to help me find my phone.

Someone make it show

Doge ⬇️ Trump ⬇️ Congress

I want to see trump get asked about it in the next presser.

Wtf is up with the typography? Every letter is from a different font face…

I (unfortunately) am in the market for a new-to-me car and I’m so pissed that my only options are either 15+ year old vehicles or spyware on wheels.

I may not rip out any antennas, but I’m damn sure going to try and interfere with them somehow.

This is the way. Layer 3 separation for services you wish to access outside of the home network and the rest of your stuff, with a VPN endpoint exposed for remote access.

It may be overkill, but I have several VLANs for specific traffic:

• DMZ - for Wireguard (and if I ever want to stand up a Honeypot)
• Services - *arr stack, some Kubes things for remote development
• IoT - any smart things like thermostat, home assistant, etc
• Trusted - primary at home network for laptops, HTPCs, etc

There are two new additions: a ext-vpn VLAN and a egress-vpn VLAN. I spun up a VM that’s dual homed running its own Wireguard/OpenVPN client on the egress side, serving DHCP on the ext-vpn side. The latter has its own wireless ssid so that anyone who connects to it is automatically on a VPN into a non-US country.